Research Interests

Artificial intelligence and machine learning influence every aspect of our modern world. In my opinion, the responsibility of research is to improve the application of these approaches by developing collaborative, privacy-preserving algorithms. These algorithms can be further improved by using already existing expert knowledge which is especially difficult to aquire in the medical sector.

Therefore, my main research interests manifest in

Informed Machine Learning
Federated Learning
Health Information Systems

Let me know, if you are looking for a final thesis, write me an e-mail or have a look at the list of theses here.

Projekte
Titel	Projektgruppe	Bild
NephroCAGE: Nephrology Disease Cooperation between Canada and Germany for Applied AI	Ali Sunyaev, Scott Thiebes, Konstantin Pandl, Florian Leiser
FLAIROP: Federated Learning for Robotic Picking	Ali Sunyaev, Scott Thiebes, Sascha Rank, Florian Leiser

Publikationsliste

2024

Knowledge-Guided Learning of Temporal Dynamics and its Application to Gas Turbines
Bielski, P.; Eismont, A.; Bach, J.; Leiser, F.; Kottonau, D.; Böhm, K.
2024. 15th ACM International Conference on Future and Sustainable Energy Systems, Singapur, 4th-7th June 2024, 279–290, Association for Computing Machinery (ACM). doi:10.1145/3632775.3661967

HILL: A Hallucination Identifier for Large Language Models
Leiser, F.; Eckhardt, S.; Leuthe, V.; Knaeble, M.; Maedche, A.; Schwabe, G.; Sunyaev, A.
2024. CHI ’24: Proceedings of the CHI Conference on Human Factors in Computing Systems. Ed.: F. Mueller, Art.-Nr.: 482, Association for Computing Machinery (ACM). doi:10.1145/3613904.3642428

HILL: A Hallucination Identifier for Large Language Models
Leiser, F.; Eckhardt, S.; Leuthe, V.; Knaeble, M.; Maedche, A.; Schwabe, G.; Sunyaev, A.
2024. arxiv. doi:10.48550/arXiv.2403.06710

Informed machine learning for cardiomegaly detection in chest X-rays: a comparative study
Hasse, F.; Leiser, F.; Sunyaev, A.
2024. Proceedings of the 21st IEEE International Symposium on Biomedical Imaging (ISBI 2024), Institute of Electrical and Electronics Engineers (IEEE)

Explainable artificial intelligence for omics data: a systematic mapping study
Toussaint, P. A.; Leiser, F.; Thiebes, S.; Schlesner, M.; Brors, B.; Sunyaev, A.
2024. Briefings in Bioinformatics, 25 (1), 1–16. doi:10.1093/bib/bbad453

2023

Medical informed machine learning: A scoping review and future research directions
Leiser, F.; Rank, S.; Schmidt-Kraepelin, M.; Thiebes, S.; Sunyaev, A.
2023. Artificial Intelligence in Medicine, 145, Art.-Nr.: 102676. doi:10.1016/j.artmed.2023.102676

Applying Random Forests in Federated Learning: A Synthesis of Aggregation Techniques
Bodynek, M.; Leiser, F.; Thiebes, S.; Sunyaev, A.
2023. Wirtschaftsinformatik 2023 Proceedings, AIS eLibrary (AISeL)

From ChatGPT to FactGPT: A Participatory Design Study to Mitigate the Effects of Large Language Model Hallucinations on Users
Leiser, F.; Eckhardt, S.; Knaeble, M.; Mädche, A.; Schwabe, G.; Sunyaev, A.
2023. Mensch und Computer 2023, 81–90, Association for Computing Machinery (ACM)

How Experts Rely on Intuition in Medical Image Annotation – A Study Proposal
Leiser, F.; Warsinsky, S. L.; Schmidt-Kraepelin, M.; Thiebes, S.; Sunyaev, A.
2023. Proceedings NeuroIS Retreat 2023 Vienna, Austria | May 30 - June 1. Ed.: F. Davis, 245–253, Springer

NephroCAGE—German-Canadian Consortium on AI for Improved Kidney Transplantation Outcome: Protocol for an Algorithm Development and Validation Study
Schapranow, M.-P.; Bayat, M.; Rasheed, A.; Naik, M.; Graf, V.; Schmidt, D.; Budde, K.; Cardinal, H.; Sapir-Pichhadze, R.; Fenninger, F.; Sherwood, K.; Keown, P.; Günther, O. P.; Pandl, K. D.; Leiser, F.; Thiebes, S.; Sunyaev, A.; Niemann, M.; Schimanski, A.; Klein, T.
2023. JMIR Research Protocols, 12, Art.-Nr.: e48892. doi:10.2196/48892

Understanding the Role of Expert Intuition in Medical Image Annotation: A Cognitive Task Analysis Approach
Leiser, F.; Warsinsky, S.; Daum, M.; Schmidt-Kraepelin, M.; Thiebes, S.; Wagner, M.; Sunyaev, A.
2023. Proceedings of the 56th Hawaii International Conference on System Sciences (HICSS 2023). Ed.: T.X. Bui, 2850–2859

2021

What Your Radiologist Might be Missing: Using Machine Learning to Identify Mislabeled Instances of X-ray Images
Rädsch, T.; Eckhardt, S.; Leiser, F.; Pandl, K. D.; Thiebes, S.; Sunyaev, A.
2021. Proceedings of the 54th Hawaii International Conference on System Sciences (HICSS)

CV

Florian Leiser ist Doktorand und wissenschaftlicher Mitarbeiter in der Forschungsgruppe Critical Information Infrastructures. Seine Forschungsinteressen umfassen Digital Health, Medical Information Systems und Federated Learning.

Ausbildung

Seit 09/2021: Doktorand an der Forschungsgruppe Critical Information Infrastructures am Karlsruher Institut für Technologie
10/2019 - 07/2021: Master of Science in Wirtschaftsinformatik, Karlsruher Institut für Technologie
10/2018 - 10/2019: Studium der Informationswirtschaft (Master of Science), Karlsruher Institut für Technologie (eingestellt)
10/2014 - 06/2018: Bachelor of Science in Informationswirtschaft, Karlsruher Institut für Technologie

Beruflicher Werdegang

Seit 09/2021: Wissenschaftlicher Mitarbeiter, Forschungsgruppe Critical Information Infrastructures, Institut für Angewandte Informatik und Formale Beschreibungsverfahren, Karlsruher Institut für Technologie
03/2019 - 02/2020: Studentische Hilfskraft bei CAS Software AG, Karlsruhe
10/2017 - 03/2018: Praktikum IT-Prüfung und Datenanalyse bei Ernst & Young GmbH, Frankfurt
10/2016 - 02/2017: Studentische Hilfskraft, Institut für Theoretische Informatik, Karlsruher Institut für Technologie
04/2016 - 09/2016: Studentische Hilfskraft, Institut für Wirtschaftsinformatik und Marketing, Karlsruher Institut für Technologie

Forschungsinteressen

Digital Health
Health Information Systems
Federated Learning